Xiao Li

xl2710 [at] princeton.edu

Hi! My name is Xiao. I'm a CS PhD student at Princeton University working on computational imaging research. I'm interested in developing novel optical systems and physical AI systems by combining hardware design with computation or machine learning. Recently, I have been focused on leveraging metalens to resolve the bottlenecks in conventional imaging and computation systems. Before coming to Princeton, I worked at Magic Leap and contributed to the display optics/waveguide design and the SLAM-based head tracking system of AR headsets. I also conducted research in Terahertz photonics at UCLA advised by Prof. Mona Jarrahi.

---

Publications

“*” stands for equal contribution.

Spatially varying nanophotonic neural networks
Kaixuan Wei , Xiao Li , Johannes Froech , Praneeth Chakravarthula, James Whitehead, Ethan Tseng, Arka Majumdar, Felix Heide
📚 Science Advances

• Summary: Demonstrated a metalens camera that performs large-kernel spatially-varying neural network convolution during the image capture. Combined with a lightweight electronic backend, this neural network outperforms AlexNet on CIFAR-10 blind test classification accuracy for the first time.
• Contribution: Device design and optimization, experimental setup, real dataset collection and calibration w.r.t. electronic ground truth

Thin On-Sensor Nanophotonic Array Cameras
Praneeth Chakravarthula, Jipeng Sun, Xiao Li , Chenyang Lei, Gene Chou, Mario Bijelic, Johannes Froesch, Arka Majumdar, Felix Heide
📚 SIGGRAPH ASIA 2023

• Summary: Demonstrated a wide FoV broadband flat camera that combines a metalens array design with probabilistic deconvolution implemented using a conditional diffusion model to improve the image quality.
• Contribution: Design and setup of the hardware prototype, dataset collection and alignment.

Seeing Through Obstructions with Diffractive Cloaking
Zheng Shi, Yuval Bahat, Seung-Hwan Baek, Qiang Fu, Hadi Amata, Xiao Li , Praneeth Chakravarthula, Wolfgang Heidrich, Felix Heide
📚 SIGGRAPH 2022

• Summary: Proposed a computational monocular camera that optically cloaks unwanted obstructions by jointly designing a diffractive optical element at the aperture plane and a feature-based deep learning reconstruction network to recover the unobstructed image.
• Contribution: Participated in discussions and assisted the experiments.

Tunable terahertz wave generation through a bimodal laser diode and plasmonic photomixer
S.-H. Yang, R. Watts, X. Li , N. Wang, V. Cojocaru, J. O’Gorman, L. P. Barry, and M. Jarrahi
📚 Optics Express

• Summary: Demonstrated a compact broadband terahertz source based on difference frequency generation by pumping a plasmonic photomixer with the dual frequencies from a two-section digital distributed feedback laser diode.
• Contribution: Device simulation and characterization

Patents

• Eyeball Camera for Display System Calibration, US 2021/0014477, WO/2021/011420, CN114128256, EP3997867
• Waveguides with High Index Materials and Methods of Fabrication thereof, US 2022/0128817, WO/2020/185954
• Systems and Methods for External Light Management, WO2020/023266, US 2021/0231951, CN113811803, EP3938824

Non-work stuff

• When I'm not playing with cameras and pixels in the lab, I like taking photos, with street photography being my favorite. Here's selected photos that I took with an iPhone.